简 历：
【工作经历】
2019年9月 — 今：中国科学院计算技术研究所，研究员
2016年9月 — 2018年6月：比利时鲁汶大学，高级访问学者
2008年3月 — 2019年9月：中国科学院计算技术研究所，副研究员
2006年11月 — 2007年12月：施乐欧洲研究中心，研究科学家
2006年2月 — 2006年10月：香港科技大学，博士后
【学习经历】
2001年9月 — 2006年1月：香港科技大学，计算机系，博士生
1998年7月 — 2001年6月：天津大学，计算机系，硕士生
1994年9月 — 1998年7月：河北工业大学，计算机系，本科生
主要论著：
部分期刊论文：
Y. Li, H. Chang, S. Shan and X. Chen. PIT: A Plug-and-Play Image Translator for Making Off-the-Shelf Models Adapt to Corruptions. IEEE Transactions on Pattern Analysis and Machine Intelligence. vol 47, issue 12: 11644 – 11661, Dec. 2025.
Keliang Li, Hong Chang, Shiguang Shan, Xilin Chen. Enhancing Robustness to Class- Conditional Distribution Shift in Long-Tailed Recognition. Transactions on Machine Learning Research. 2024.
Ruibing Hou, Hong Chang, Bingpeng Ma, Shiguang Shan and Xilin Chen, Triplet Adaptation Framework for Robust Semi-Supervised Learning, IEEE Trans. Pattern Anal. Mach. Intell. 46(12), pp. 8056-8073, December 2024.
Ruibing Hou, Hong Chang, Bingpeng Ma, Shiguang Shan, Xilin Chen: Dual Compensation Residual Networks for Class Imbalanced Learning. IEEE Trans. Pattern Anal. Mach. Intell. 45(10): 11733-11752, 2023.
Ruibing Hou, Bingpeng Ma, Hong Chang, Xinqian Gu, Shiguang Shan, Xilin Chen: Feature Completion for Occluded Person Re-Identification. IEEE Trans. Pattern Anal. Mach. Intell. 44(9): 4894-4912, 2022.
Xinqian Gu, Hong Chang, Bingpeng Ma, Shiguang Shan: Motion Feature Aggregation for Video-Based Person Re-Identification. IEEE Trans. Image Process. 31: 3908-3919, 2022.
Kongming Liang, Hong Chang, Bingpeng Ma, Shiguang Shan, Xilin Chen: Unifying Visual Attribute Learning with Object Recognition in a Multiplicative Framework. IEEE Trans. Pattern Anal. Mach. Intell. 41(7): 1747-1760, 2019.
Deming Zhai, Hong Chang, Shiguang Shan, Xilin Chen, Wen Gao: Multiview Metric Learning with Global Consistency and Local Smoothness. ACM Trans. Intell. Syst. Technol. 3(3): 53:1-53:22, 2012.
近年会议论文：
Mengdi Liu, Xiaoxue Cheng, Zhangyang Gao, Hong Chang, Cheng Tan, Shiguang Shan, Xilin Chen. ProtInvTree: Deliberate Protein Inverse Folding with Reward-guided Tree Search. NeurIPS 2025.
Zaifei Yang, Hong Chang, Ruibing Hou, Shiguang Shan, Xilin Chen. KnowMol: Advancing Molecular Large Language Models with Multi-Level Chemical Knowledge. NeurIPS 2025.
Yinqi Li, Jiahe Zhao, Hong Chang, Ruibing Hou, Shiguang Shan, Xilin Chen. un2CLIP: Improving CLIP's Visual Detail Capturing Ability via Inverting unCLIP. NeurIPS 2025.
Jiachen Liang, Ruibing Hou, Minyang Hu, Hong Chang, Shiguang Shan, Xilin Chen. Revisiting Logit Distributions for Reliable Out-of-Distribution Detection. NeurIPS 2025.
Mengdi Liu, Zhangyang Gao, Hong Chang, Stan Z. Li, Shiguang Shan, Xilin Chen. G2PDiffusion: Genotype-to-Phenotype Prediction with Diffusion Models. ICCV 2025.
Wen Wang, Ruibing Hou, Hong Chang, Shiguang Shan, Xilin Chen. MATS: An Audio Language Model under Text-only Supervision. ICML 2025.
Jiahe Zhao, Ruibing Hou, Zejie Tian, Hong Chang, Shiguang Shan. HIS-GPT: Towards 3D Human-In-Scene Multimodal Understanding. ICCV 2025.
Zhuo Li, Mingshuang Luo, Ruibing Hou, Xin Zhao, Hao Liu, Hong Chang, Zimo Liu, Chen Li. Morph: A Motion-free Physics Optimization Framework for Human Motion Generation. ICCV 2025.
Yiheng Li, Ruibing Hou, Hong Chang, Shiguang Shan, Xilin Chen. UniPose: A Unified Multimodal Framework for Human Pose Comprehension, Generation and Editing. CVPR 2025.
Jiachen Liang, RuiBing Hou, Minyang Hu, Hong Chang, Shiguang Shan, Xilin Chen. UMFC: Unsupervised Multi-Domain Feature Calibration for Vision-Language Models. NeurIPS 2024.
Minyang Hu, Hong Chang, Bingpeng Ma, Shiguang Shan, Xilin Chen. Scalable Modular Network: A Framework for Adaptive Learning via Agreement Routing. ICLR, 2024.
Mingshuang Luo, Ruibing Hou, Zhuo Li, Hong Chang, Zimo Liu, Yaowei Wang, Shiguang Shan. M3GPT: An Advanced Multimodal, Multitask Framework for Motion Comprehension and Generation. NeurIPS 2024.
Jiachen Liang, Ruibing Hou, Minyang Hu, Hong Chang, Shiguang Shan, Xilin Chen. UMFC: Unsupervised Multi-Domain Feature Calibration for Vision-Language Models. NeurIPS 2024.
Jinjing Hu, Wenrui Liu, Hong Chang, Bingpeng Ma, Shiguang Shan, Xilin Chen. An Information Theoretical View for Out-Of-Distribution Detection. ECCV. 2024.
Wenrui Liu, Hong Chang, Bingpeng Ma, Shiguang Shan, Xilin Chen: Diversity-Measurable Anomaly Detection. CVPR 2023.
Minyang Hu, Hong Chang, Zong Guo, Bingpeng Ma, Shiguang Shan, Xilin Chen. Understanding Few-Shot Learning: Measuring Task Relatedness and Adaptation Difficulty via Attributes. NeurIPS 2023.
Minyang Hu, Hong Chang, Bingpeng Ma, Shiguang Shan: Learning Continuous Graph Structure with Bilevel Programming for Graph Neural Networks. IJCAI 2022.
Yinqi Li, Hong Chang, Bingpeng Ma, Shiguang Shan, Xilin Chen: Optimal Positive Generation via Latent Transformation for Contrastive Learning. NeurIPS 2022.
Ruibing Hou, Hong Chang, Bingpeng Ma, Shiguang Shan, Xilin Chen: Cross Attention Network for Few-shot Classification. NeurIPS 2019.
更完整的论文列表请参见Google Scholar页面：
https://scholar.google.com/citations?user=LX6MnNsAAAAJ&hl=en
【教学工作】
《概率论与数理统计》中国科学院大学本科课程
《机器学习》中国科学院计算技术研究所博士课程
科研项目：
[1] 国家自然科学基金面上项目，“面向视觉特征表示的元学习方法研究”，2020/01-2023/12，项目负责人
[2] 北京市自然科学基金，“面向小样本医疗数据的深度学习方法研究及在脊柱肿瘤诊断中的应用”，2018/12-2021/12，项目骨干
[3] 国家自然科学基金重大项目“云环境下的图像视频群体协同表达与处理”之课题五，“面向群体数据的AVS云媒体标准及验证平台”，2014/01-2018/12，合作单位负责人
[4] 国家自然科学基金面上项目，61272319，“面向图像与视频特征表示的深度编码方法研究”，2013/01-2016/12，项目负责人
[5] 国家自然科学基金青年基金项目，“面向图像识别的半监督距离度量方法研究”，2009/01-2011/12，项目负责人
常虹 研究员
研究方向：
所属部门：智能信息处理重点实验室、智能算法安全全国重点实验室
导师类别：博导计算机应用技术
联系方式：changhong@ict.ac.cn
个人网页：https://vipl.ict.ac.cn/people/~hchang